See hyperparameter on Wiktionary
{
"derived": [
{
"_dis1": "0 0",
"word": "hyperparametric"
}
],
"etymology_templates": [
{
"args": {
"1": "en",
"2": "hyper",
"3": "parameter"
},
"expansion": "hyper- + parameter",
"name": "prefix"
}
],
"etymology_text": "From hyper- + parameter.",
"forms": [
{
"form": "hyperparameters",
"tags": [
"plural"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "hyperparameter (plural hyperparameters)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"related": [
{
"_dis1": "0 0",
"word": "hyperprior"
}
],
"senses": [
{
"categories": [
{
"kind": "topical",
"langcode": "en",
"name": "Statistics",
"orig": "en:Statistics",
"parents": [
"Formal sciences",
"Mathematics",
"Sciences",
"All topics",
"Fundamental"
],
"source": "w"
},
{
"_dis": "57 43",
"kind": "other",
"name": "English entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "73 27",
"kind": "other",
"name": "English terms prefixed with hyper-",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "60 40",
"kind": "other",
"name": "Entries with translation boxes",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "59 41",
"kind": "other",
"name": "Pages with 1 entry",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "62 38",
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "70 30",
"kind": "other",
"name": "Terms with Finnish translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "68 32",
"kind": "other",
"name": "Terms with French translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "70 30",
"kind": "other",
"name": "Terms with German translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "68 32",
"kind": "other",
"name": "Terms with Portuguese translations",
"parents": [],
"source": "w+disamb"
}
],
"examples": [
{
"text": "this model has four hyperparameters",
"type": "example"
},
{
"ref": "2003, Gary Koop, Bayesian Econometrics, John Wiley & Sons Ltd., page 19:",
"text": "The exact interpretation of these hyperparameters becomes clearer once you have seen their role in the posterior and, hence, we defer a deeper discussion of prior elicitation until the next section.",
"type": "quote"
}
],
"glosses": [
"A parameter of a prior (as distinguished from inferred parameters of the model for the underlying system under analysis)."
],
"id": "en-hyperparameter-en-noun-iAIeaQ-X",
"links": [
[
"Bayesian",
"Bayesian"
],
[
"statistics",
"statistics"
],
[
"parameter",
"parameter"
],
[
"prior",
"prior#Noun"
],
[
"model",
"model"
]
],
"qualifier": "Bayesian statistics",
"raw_glosses": [
"(Bayesian statistics) A parameter of a prior (as distinguished from inferred parameters of the model for the underlying system under analysis)."
],
"synonyms": [
{
"word": "superparameter"
}
],
"translations": [
{
"_dis1": "72 28",
"code": "fi",
"lang": "Finnish",
"sense": "in Bayesian statistics, a parameter of a prior",
"word": "hyperparametri"
},
{
"_dis1": "72 28",
"code": "fr",
"lang": "French",
"sense": "in Bayesian statistics, a parameter of a prior",
"word": "hyperparamètre"
},
{
"_dis1": "72 28",
"code": "de",
"lang": "German",
"sense": "in Bayesian statistics, a parameter of a prior",
"tags": [
"masculine"
],
"word": "Hyperparameter"
},
{
"_dis1": "72 28",
"code": "pt",
"lang": "Portuguese",
"sense": "in Bayesian statistics, a parameter of a prior",
"tags": [
"masculine"
],
"word": "hiperparâmetro"
}
]
},
{
"categories": [
{
"kind": "topical",
"langcode": "en",
"name": "Machine learning",
"orig": "en:Machine learning",
"parents": [
"Artificial intelligence",
"Computer science",
"Cybernetics",
"Computing",
"Sciences",
"Applied mathematics",
"Systems theory",
"Technology",
"All topics",
"Mathematics",
"Systems",
"Fundamental",
"Formal sciences",
"Interdisciplinary fields",
"Society"
],
"source": "w"
}
],
"examples": [
{
"ref": "2016, Ian Goodfellow, Yoshua Bengio, Aaron Courville, chapter 11, in Deep Learning, MIT Press, →ISBN, page 420:",
"text": "The ideal learning algorithm just takes a dataset and outputs a function, without requiring hand tuning of hyperparameters.",
"type": "quote"
},
{
"ref": "2024 May 4, Alex Hern, Dan Milmo, quoting James Betker, “Danger and opportunity for news industry as AI woos it for vital human-written copy”, in The Guardian, →ISSN:",
"text": "“Model behaviour is not determined by architecture, hyperparameters, or optimizer choices,” he said, referring to the technical difficulties of training a language model. “It’s determined by your dataset, nothing else. […]”",
"type": "quote"
}
],
"glosses": [
"A parameter whose value is set before the learning process begins."
],
"id": "en-hyperparameter-en-noun-KljUWOIE",
"links": [
[
"machine learning",
"machine learning"
]
],
"qualifier": "machine learning",
"raw_glosses": [
"(machine learning) A parameter whose value is set before the learning process begins."
]
}
],
"word": "hyperparameter"
}
{
"categories": [
"English countable nouns",
"English entries with incorrect language header",
"English lemmas",
"English nouns",
"English terms prefixed with hyper-",
"Entries with translation boxes",
"Pages with 1 entry",
"Pages with entries",
"Terms with Finnish translations",
"Terms with French translations",
"Terms with German translations",
"Terms with Portuguese translations"
],
"derived": [
{
"word": "hyperparametric"
}
],
"etymology_templates": [
{
"args": {
"1": "en",
"2": "hyper",
"3": "parameter"
},
"expansion": "hyper- + parameter",
"name": "prefix"
}
],
"etymology_text": "From hyper- + parameter.",
"forms": [
{
"form": "hyperparameters",
"tags": [
"plural"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "hyperparameter (plural hyperparameters)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"related": [
{
"word": "hyperprior"
}
],
"senses": [
{
"categories": [
"English terms with quotations",
"English terms with usage examples",
"en:Statistics"
],
"examples": [
{
"text": "this model has four hyperparameters",
"type": "example"
},
{
"ref": "2003, Gary Koop, Bayesian Econometrics, John Wiley & Sons Ltd., page 19:",
"text": "The exact interpretation of these hyperparameters becomes clearer once you have seen their role in the posterior and, hence, we defer a deeper discussion of prior elicitation until the next section.",
"type": "quote"
}
],
"glosses": [
"A parameter of a prior (as distinguished from inferred parameters of the model for the underlying system under analysis)."
],
"links": [
[
"Bayesian",
"Bayesian"
],
[
"statistics",
"statistics"
],
[
"parameter",
"parameter"
],
[
"prior",
"prior#Noun"
],
[
"model",
"model"
]
],
"qualifier": "Bayesian statistics",
"raw_glosses": [
"(Bayesian statistics) A parameter of a prior (as distinguished from inferred parameters of the model for the underlying system under analysis)."
],
"synonyms": [
{
"word": "superparameter"
}
]
},
{
"categories": [
"English terms with quotations",
"en:Machine learning"
],
"examples": [
{
"ref": "2016, Ian Goodfellow, Yoshua Bengio, Aaron Courville, chapter 11, in Deep Learning, MIT Press, →ISBN, page 420:",
"text": "The ideal learning algorithm just takes a dataset and outputs a function, without requiring hand tuning of hyperparameters.",
"type": "quote"
},
{
"ref": "2024 May 4, Alex Hern, Dan Milmo, quoting James Betker, “Danger and opportunity for news industry as AI woos it for vital human-written copy”, in The Guardian, →ISSN:",
"text": "“Model behaviour is not determined by architecture, hyperparameters, or optimizer choices,” he said, referring to the technical difficulties of training a language model. “It’s determined by your dataset, nothing else. […]”",
"type": "quote"
}
],
"glosses": [
"A parameter whose value is set before the learning process begins."
],
"links": [
[
"machine learning",
"machine learning"
]
],
"qualifier": "machine learning",
"raw_glosses": [
"(machine learning) A parameter whose value is set before the learning process begins."
]
}
],
"translations": [
{
"code": "fi",
"lang": "Finnish",
"sense": "in Bayesian statistics, a parameter of a prior",
"word": "hyperparametri"
},
{
"code": "fr",
"lang": "French",
"sense": "in Bayesian statistics, a parameter of a prior",
"word": "hyperparamètre"
},
{
"code": "de",
"lang": "German",
"sense": "in Bayesian statistics, a parameter of a prior",
"tags": [
"masculine"
],
"word": "Hyperparameter"
},
{
"code": "pt",
"lang": "Portuguese",
"sense": "in Bayesian statistics, a parameter of a prior",
"tags": [
"masculine"
],
"word": "hiperparâmetro"
}
],
"word": "hyperparameter"
}
Download raw JSONL data for hyperparameter meaning in All languages combined (3.5kB)
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2024-12-15 from the enwiktionary dump dated 2024-12-04 using wiktextract (8a39820 and 4401a4c). The data shown on this site has been post-processed and various details (e.g., extra categories) removed, some information disambiguated, and additional data merged from other sources. See the raw data download page for the unprocessed wiktextract data.
If you use this data in academic research, please cite Tatu Ylonen: Wiktextract: Wiktionary as Machine-Readable Structured Data, Proceedings of the 13th Conference on Language Resources and Evaluation (LREC), pp. 1317-1325, Marseille, 20-25 June 2022. Linking to the relevant page(s) under https://kaikki.org would also be greatly appreciated.